Paper Info
Title
Learning to detect roads in high-resolution aerial images
Abstract
Reliably extracting information from aerial imagery is a difficult problem with many practical applications. One specific case of this problem is the task of automatically detecting roads. This task is a difficult vision problem because of occlusions, shadows, and a wide variety of non-road objects. Despite 30 years of work on automatic road detection, no automatic or semi-automatic road detection system is currently on the market and no published method has been shown to work reliably on large datasets of urban imagery. We propose detecting roads using a neural network with millions of trainable weights which looks at a much larger context than was used in previous attempts at learning the task. The network is trained on massive amounts of data using a consumer GPU. We demonstrate that predictive performance can be substantially improved by initializing the feature detectors using recently developed unsupervised learning methods as well as by taking advantage of the local spatial coherence of the output labels.We show that our method works reliably on two challenging urban datasets that are an order of magnitude larger than what was used to evaluate previous approaches.
Year
DOI
Venue
2010
10.1007/978-3-642-15567-3_16
ECCV (6)
Keywords
Field
DocType
challenging urban datasets,difficult problem,neural network,larger context,large datasets,previous attempt,high-resolution aerial image,difficult vision problem,previous approach,automatic road detection,aerial imagery,unsupervised learning,high resolution
Computer vision,Stochastic gradient descent,Vision problem,CUDA,Computer science,Aerial image,Unsupervised learning,Artificial intelligence,Initialization,Artificial neural network,Aerial imagery,Machine learning
Conference
Volume
ISSN
ISBN
6316
0302-9743
3-642-15566-9
Citations 
PageRank 
References 
33
3.15
14
Authors
2
Name
Order
Citations
PageRank
Volodymyr Mnih13796158.28
geoffrey e hinton2404354751.69